RESUMO
Depression is recognized as a significant public health issue in the United States. The National Survey on Drug Use and Health reports that 21.0 million adults aged 18 or older had major depressive disorder in 2020, including 14.8 million experiencing a major depressive episode with severe impairment. The aim is to predict the positivity of Patient Health Questionnaire-2 (PHQ-2) outcomes among patients in primary care settings by analyzing a range of variables, including socioeconomic status, demographic characteristics, and health behaviors, thereby identifying those at increased risk for depression. Employing a machine learning approach, the study utilizes retrospective data from electronic health records across 15 primary care clinics in South Florida to explore the relationship between social determinants of health (SDoH), including area of deprivation index (ADI) and PHQ-2 positivity. The study encompasses 15 primary care clinics located in South Florida, where a diverse patient population receives care. Analysis included 94,572 patient visits; 74,636 records were included in the study. If a zip+4 was not available or an ADI score did not exist, the visit was not included in the final analysis. Screening involved the PHQ-2, assessing depressed mood and anhedonia, with a cutoff >2 indicating positive screening. ADI was used to assess SDoH by matching patients' residential postal codes to ADI national percentiles. Demographics, sexual history, tobacco use, caffeine intake, and community involvement were also evaluated in the study. Over 40 machine learning algorithms were explored for their accuracy in predicting PHQ-2 outcomes, using software tools including Scikit-learn and stats models in Python. Variables were normalized, scored, and then subjected to predictive regression models, with Random Forest showing outstanding performance. Feature engineering and correlation analysis identified ADI, age, education, visit type, coffee intake, and marital status as significant predictors of PHQ-2 positivity. The area under the curve and model accuracies varied across clinics, with specific clinics showing higher predictive accuracy and others (p > .05). The study concludes that the ADI, as a proxy for SDoH, alongside other individual factors, can predict PHQ-2 positivity. Health organizations can use this information to anticipate health needs and resource allocation.
Assuntos
Questionário de Saúde do Paciente , Atenção Primária à Saúde , Humanos , Feminino , Masculino , Florida , Estudos Retrospectivos , Pessoa de Meia-Idade , Adulto , Aprendizado de Máquina , Programas de Rastreamento , Inquéritos e Questionários , Determinantes Sociais da Saúde , Depressão/diagnósticoRESUMO
Introducción: La enfermedad mental es una de las afecciones que genera más discapacidad en el mundo. Se estima que 1 de cada 4 personas la padece o la ha padecido en su vida. Desde sus inicios, la enfermedad mental ha estado ligada a la estigmatización y el prejuicio, con implicaciones importantes para el ejercicio de derechos humanos, incluido el de la salud, pues impiden su detección y su adecuado tratamiento. Eliminar el estigma requiere intervenciones variadas, especialmente la participación de las personas con estos trastornos. Las redes sociales virtuales son una alternativa para que ellas y otras interesadas interactúen en pro de aclarar inquietudes y modificar la situación de exclusión. Método: Descripción de la experiencia del grupo de opinión y apoyo en Facebook «Aceptando mentes dementes¼, dirigido a personas con trastorno mental, familiares y otros, buscando hacer visible el problema del estigma y contribuir a evitar sus consecuencias. Análisis de la información cuantitativa y cualitativa recogida en 2,5 años de funcionamiento del grupo, conformado por 764 miembros de distintos países. Resultados: Se alcanzaron los propósitos del grupo de difusión de información, interacción asociada con la manifestación de experiencias y obtención de apoyo. Conclusiones: La red social virtual permite, con bajos costes, conformar comunidades con necesidades específicas y brindar apoyo. La puesta en público del estigma ligado a la enfermedad mental ayuda a crear conciencia y generar opciones de cambio. Para mantener el grupo y vincularlo a otros recursos se incluirá en el espacio virtual www.mentalpuntoapoyo.com.
Introduction: Mental illness is one of the diseases that generates more disability worldwide, and it is estimated that one in four people has or has had this kind of illness during their lives. Since the beginning, mental illness has been frequently linked to stigma and prejudice, which has important implications for the exercise of their human rights, including the right to health, as these preconceptions can delay their early detection and timely treatment. Eliminating stigma requires multiple interventions, in which the participation of people with these illnesses can be very helpful. Social networks portray an alternative for them and for people interested in this topic, helping them interact, clarify some concerns and doubts, and perhaps even modify their exclusion status. Method: Describing the experience of the opinion and support group on Facebook called "Aceptando mentes dementes" ("Accepting Demented Minds"), created for people with mental illnesses, their families and any person interested in this matter, which seeks to make the impact and consequences that result from stigma more noticable. Analysis of qualitative and quantitative data collected over two and a half years of operation of the group, formed by 764 members from different countries. Results: The aims of the group, as regards the spreading of information, interaction through shared experiences, and obtaining support were reached. Conclusions: Social networks allow the creation of communities that share specific needs, such as understanding and support, and all this at low cost. Knowing and being conscious about the stigma linked to mental illness helps raise awareness and generate options for change. To maintain and link it to other resources, the group will be included in the web site www.mentalpuntoapoyo.com.